mercurial/repair.py

rebase: allow collapsing branches in place (issue3111)

We allow rebase plus collapse, but not collapse only? I imagine people would
rebase first then collapse once they are sure the rebase is correct and it is
the right time to finish it.

I was reluctant to submit this patch for reasons detailed below, but it
improves rebase --collapse usefulness so much it is worth the ugliness.

The fix is ugly because we should be fixing the collapse code path rather than
the merge. Collapsing by merging changesets repeatedly is inefficient compared
to what commit --amend does: commitctx(), update, strip. The problem with the
latter is, to generate the synthetic changeset, copy records are gathered with
copies.pathcopies(). copies.pathcopies() is still implemented with merging in
mind and discards information like file replaced by the copy of another,
criss-cross copies and so forth. I believe this information should not be lost,
even if we decide not to interpret it fully later, at merge time.

The second issue with improving rebase --collapse is the option should not be
there to begin with. Rebasing and collapsing are orthogonal and a dedicated
command would probably enable a better, simpler ui. We should avoid advertizing
rebase --collapse, but with this fix it becomes the best shipped solution to
collapse changesets.

And for the record, available techniques are:
- revert + commit + strip: lose copies
- mq/qfold: repeated patching() (mostly correct, fragile)
- rebase: repeated merges (mostly correct, fragile)
- collapse: revert + tag rewriting wizardry, lose copies
- histedit: repeated patching() (mostly correct, fragile)
- amend: copies.pathcopies() + commitctx() + update + strip

# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <[e-mail]>
# Copyright 2007 Matt Mackall
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from mercurial import changegroup, bookmarks
from mercurial.node import short
from mercurial.i18n import _
import os
import errno

def _bundle(repo, bases, heads, node, suffix, compress=True):
    """create a bundle with the specified revisions as a backup"""
    cg = repo.changegroupsubset(bases, heads, 'strip')
    backupdir = repo.join("strip-backup")
    if not os.path.isdir(backupdir):
        os.mkdir(backupdir)
    name = os.path.join(backupdir, "%s-%s.hg" % (short(node), suffix))
    if compress:
        bundletype = "HG10BZ"
    else:
        bundletype = "HG10UN"
    return changegroup.writebundle(cg, name, bundletype)

def _collectfiles(repo, striprev):
    """find out the filelogs affected by the strip"""
    files = set()

    for x in xrange(striprev, len(repo)):
        files.update(repo[x].files())

    return sorted(files)

def _collectbrokencsets(repo, files, striprev):
    """return the changesets which will be broken by the truncation"""
    s = set()
    def collectone(revlog):
        linkgen = (revlog.linkrev(i) for i in revlog)
        # find the truncation point of the revlog
        for lrev in linkgen:
            if lrev >= striprev:
                break
        # see if any revision after this point has a linkrev
        # less than striprev (those will be broken by strip)
        for lrev in linkgen:
            if lrev < striprev:
                s.add(lrev)

    collectone(repo.manifest)
    for fname in files:
        collectone(repo.file(fname))

    return s

def strip(ui, repo, nodelist, backup="all", topic='backup'):
    cl = repo.changelog
    # TODO handle undo of merge sets
    if isinstance(nodelist, str):
        nodelist = [nodelist]
    striplist = [cl.rev(node) for node in nodelist]
    striprev = min(striplist)

    keeppartialbundle = backup == 'strip'

    # Some revisions with rev > striprev may not be descendants of striprev.
    # We have to find these revisions and put them in a bundle, so that
    # we can restore them after the truncations.
    # To create the bundle we use repo.changegroupsubset which requires
    # the list of heads and bases of the set of interesting revisions.
    # (head = revision in the set that has no descendant in the set;
    #  base = revision in the set that has no ancestor in the set)
    tostrip = set(striplist)
    for rev in striplist:
        for desc in cl.descendants(rev):
            tostrip.add(desc)

    files = _collectfiles(repo, striprev)
    saverevs = _collectbrokencsets(repo, files, striprev)

    # compute heads
    saveheads = set(saverevs)
    for r in xrange(striprev + 1, len(cl)):
        if r not in tostrip:
            saverevs.add(r)
            saveheads.difference_update(cl.parentrevs(r))
            saveheads.add(r)
    saveheads = [cl.node(r) for r in saveheads]

    # compute base nodes
    if saverevs:
        descendants = set(cl.descendants(*saverevs))
        saverevs.difference_update(descendants)
    savebases = [cl.node(r) for r in saverevs]
    stripbases = [cl.node(r) for r in tostrip]

    bm = repo._bookmarks
    updatebm = []
    for m in bm:
        rev = repo[bm[m]].rev()
        if rev in tostrip:
            updatebm.append(m)

    # create a changegroup for all the branches we need to keep
    backupfile = None
    if backup == "all":
        backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
        repo.ui.status(_("saved backup bundle to %s\n") % backupfile)
    if saveheads or savebases:
        # do not compress partial bundle if we remove it from disk later
        chgrpfile = _bundle(repo, savebases, saveheads, node, 'temp',
                            compress=keeppartialbundle)

    mfst = repo.manifest

    tr = repo.transaction("strip")
    offset = len(tr.entries)

    try:
        tr.startgroup()
        cl.strip(striprev, tr)
        mfst.strip(striprev, tr)
        for fn in files:
            repo.file(fn).strip(striprev, tr)
        tr.endgroup()

        try:
            for i in xrange(offset, len(tr.entries)):
                file, troffset, ignore = tr.entries[i]
                repo.sopener(file, 'a').truncate(troffset)
            tr.close()
        except:
            tr.abort()
            raise

        if saveheads or savebases:
            ui.note(_("adding branch\n"))
            f = open(chgrpfile, "rb")
            gen = changegroup.readbundle(f, chgrpfile)
            if not repo.ui.verbose:
                # silence internal shuffling chatter
                repo.ui.pushbuffer()
            repo.addchangegroup(gen, 'strip', 'bundle:' + chgrpfile, True)
            if not repo.ui.verbose:
                repo.ui.popbuffer()
            f.close()
            if not keeppartialbundle:
                os.unlink(chgrpfile)

        # remove undo files
        for undofile in repo.undofiles():
            try:
                os.unlink(undofile)
            except OSError, e:
                if e.errno != errno.ENOENT:
                    ui.warn(_('error removing %s: %s\n') % (undofile, str(e)))

        for m in updatebm:
            bm[m] = repo['.'].node()
        bookmarks.write(repo)
    except:
        if backupfile:
            ui.warn(_("strip failed, full bundle stored in '%s'\n")
                    % backupfile)
        elif saveheads:
            ui.warn(_("strip failed, partial bundle stored in '%s'\n")
                    % chgrpfile)
        raise

    repo.destroyed()